
    fi                         d Z ddlZddlZddlZddlmZ ddlmZ ddedej	        fdZ
ed	k    r e
d
          Z ee           dS dS )uO   
Date: 2024/4/25 17:00
Desc: 新闻联播文字稿
https://tv.cctv.com/lm/xwlb
    N)BeautifulSoup)tqdm20240424datereturnc                    t          |           t          d          k    rd|  d}t          j        |          }d|_        t	          j        d|j                  }d |dd         D             }g }g }d	d
ddddddddd
}t          |d          D ]J}	 t          j        ||          }d|_        t          |j        d          }	|		                    d          j        }
|		                    dddi          j        }|
                    |
                    d                                                              dd                     |
                    |                                                    d                               d!                              d"                                                              dd                     D#  Y IxY wt          j        | gt          |          z  ||gg d#$          j        }|S t          |           t          d%          k     rd|  d}t          j        |          }d|_        t          |j        d          }	d& |		                    dd'd(i)                              d*          dd         D             }g }g }d	d
ddddddddd
}t          |d          D ]K}	 t          j        ||          }d|_        t          |j        d+          }	|		                    d          j        }
|		                    dddi)          j        }|
                    |
                    d                                                              dd                     |
                    |                                                    d                               d!                              d"                                                              dd                     E#  Y JxY wt          j        | gt          |          z  ||gg d#$          j        }|S t          |           t          d%          k    rkd,|  d}t          j        |          }d|_        t          |j        d          }	d- |	                    d*          dd         D             }g }g }d	d
ddddddddd
}t          |d          D ]}	 t          j        ||          }d|_        t          |j        d+          }	|		                    d          r|		                    d          j        }
n|		                    ddd.i)          j        }
|		                    dddi)          r|		                    dddi)          j        }n|		                    ddd/i)          j        }|
                    |
                    d                                                              dd                     |
                    |                                                    d                               d!                              d"                                                              dd                     #  Y xY wt          j        | gt          |          z  ||gg d#$          j        }|S dS )0u   
    新闻联播文字稿
    https://tv.cctv.com/lm/xwlb
    :param date: 需要获取数据的日期; 目前 20160203 年后
    :type date: str
    :return: 新闻联播文字稿
    :rtype: pandas.DataFrame
    20130708z%https://cctv.cntv.cn/lm/xinwenlianbo/z.shtmlgbkztitle_array_01\((.*)c                 v    g | ]6}t          j        d |          d                             d          d         7S )z(http.*)r   ')refindallsplit.0items     A/usr/local/lib/python3.11/dist-packages/akshare/news/news_cctv.py
<listcomp>znews_cctv.<locals>.<listcomp>   sI     
 
 
>BBJz4((+11#66q9
 
 
       Nztext/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9zgzip, deflatezzh-CN,zh;q=0.9,en;q=0.8zno-cachezcna=DLYSGBDthG4CAbRVCNxSxGT6ztv.cctv.comz
keep-alive1zsMozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36)
AcceptzAccept-EncodingzAccept-LanguagezCache-ControlCookieHostPragmazProxy-ConnectionzUpgrade-Insecure-Requestsz
User-AgentF)leave)headerszutf-8lxmlh3divclasscnt_bd)attrsu   [视频]
 u    央视网消息(新闻联播)：u$   央视网消息（新闻联播）：u   (新闻联播)：)r   titlecontent)dataindex20160203c                 D    g | ]}|                     d           d         S ahreffindr   s     r   r   znews_cctv.<locals>.<listcomp>O   s7     
 
 
 IIcNN6"
 
 
r   idcontentELMT1368521805488378)namer#   li)featuresz https://tv.cctv.com/lm/xwlb/day/c                 D    g | ]}|                     d           d         S r,   r/   r   s     r   r   znews_cctv.<locals>.<listcomp>   s'    OOOtDIIcNN6*OOOr   titcontent_area)intrequestsgetencodingr   r   textr   r   r0   appendstripreplacepd	DataFramelenTfind_all)r   urlrraw_listpage_url
title_listcontent_listr   pagesoupr&   r'   temp_dfs                r   	news_cctvrO      s2    4yyC
OO##BdBBBL
:5qv>>
 
FNqrrl
 
 
 
U.8'4!  ,),1
 
 /// 	 	DLw777$
$QVV44		$,))E'81D)EEJ!!%++j"9"9"?"?"A"A"I"I$PS"T"TUUU##MMOOU=>>UABBU.//UWWWT3''   ,&3z??*JE...
 
 
  	 	TS__	$	$BdBBBL
QVV,,
 
		4)F"G "  htnnQRR!
 
 
 
J.8'4!  ,),1
 
 /// 	 	DLw777$
$QVf===		$,))w6I)JJO!!%++j"9"9"?"?"A"A"I"I$PS"T"TUUU##MMOOU=>>UABBU.//UWWWT3''   ,&3z??*JE...
 
 
  	 	TS__	$	$====L
QVV,,OOt}}T7J7J1227NOOO
J.8'4!  ,),1
 
 /// 	 	DLw777$
$QVf===99T?? O IIdOO0EE II5%8HIIINE99%/B9CC "iiU7H:MiNNSGG"ii"7N*C (    !!%++j"9"9"?"?"A"A"I"I$PS"T"TUUU##MMOOU=>>UABBU.//UWWWT3''   ,&3z??*JE...
 
 
  	 i 
%	$s'   D>GGD?PP-F+ZZ__main__)r   )r   )__doc__r   pandasrA   r:   bs4r   r   strrB   rO   __name__news_cctv_dfprint r   r   <module>rY      s     
			                 _ _C _ _ _ _ _D z9*---L	E, r   